Jongmin Lee

Hi! I am a Ph.D. student at Seoul National University advised by Ernest K. Ryu.

My research interests lie in optimization and reinforcement learning theory, with a particular focus on their intersection. Specifically, I am interested in leveraging optimization techniques to enhance the convergence of reinforcement learning algorithms.

Contact : dlwhd2000@snu.ac.kr
Google Scholar

Pubilication

(C: Conference, J: Journal, P: Preprint, *: Equal contribution)

[C5] Near-Optimal Sample Complexity for MDPs via Anchoring

Jongmin Lee, Mario Bravo, Roberto Cominetti
International Conference on Machine Learning (ICML), 2025

[C4] Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Process

Jongmin Lee, Ernest K. Ryu
Internation Conference on Representation Learning (ICLR), 2025

[C3] Accelerating Value Iteration with Anchoring

Jongmin Lee, Ernest K. Ryu
Advances in Neural Information Processing Systems (NeurIPS), 2023

[C2] Neural Tangent Kernel Analysis of Deep Narrow Neural Networks

Jongmin Lee, Joo Young Choi, Ernest K. Ryu, Albert No
International Conference on Machine Learning (ICML), 2022

[C1] A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast

Jongmin Lee, Chanwoo Park, Ernest K. Ryu
Advances in Neural Information Processing Systems (NeurIPS), 2021

[J2] Deflated Dynamics Value Iteration

Jongmin Lee, Amin Rakhsha, Ernest K Ryu, Amir-massoud Farahmand
Transactions on Machine Learning Research (TMLR), 2025

[J1] Convergence Analyses of Davis-Yin Splitting via Scaled Relative Graphs

Jongmin Lee*, Sohuen Yi*, Ernest K. Ryu
SIAM Journal on Optimization, 2025

Education

Seoul National University (SNU), Sep 2023 - Present (advisor: Ernest K. Ryu)

Ph.D. in Mathematics

Seoul National University (SNU), Sep 2020 - August 2023 (advisor: Ernest K. Ryu)

M.S. in Mathematics

Korea Advanced Institute of Science and Technology (KAIST), Mar 2012 - Feb 2020

B.S. in Mathematics

Experiences

Collaborator, Pontificia Universidad Católica de Chile, Dec 2024 - Feb 2025 (Roberto Cominetti and Mario Bravo)

Research Intern, Vector Institute, May 2023 - Aug 2023 (advisor: Amir-massoud Farahmand)

Military Service, Army sergeant, Sep 2015 - June 2017

Invited talks

RL theory seminar, Feb 2025, "Accelerating Value Iteration with Anchoring"

AGCO seminar, University of Chile, Aug 2024, "Convergence Analysis of Davis-Yin Splitting via Scaled Relative Graph"

Awards

Youlchon Fellowship, SNU AI, 2022

Page updated

Report abuse